Defining subpopulations of differential drug response to reveal novel target populations

Personalised medicine has predominantly focused on genetically altered cancer genes that stratify drug responses, but there is a need to objectively evaluate differential pharmacology patterns at a subpopulation level. Here, we introduce an approach based on unsupervised machine learning to compare the pharmacological response relationships between 327 pairs of cancer therapies. This approach integrated multiple measures of response to identify subpopulations that react differently to inhibitors of the same or different targets to understand mechanisms of resistance and pathway cross-talk. MEK, BRAF, and PI3K inhibitors were shown to be effective as combination therapies for particular BRAF mutant subpopulations. A systematic analysis of preclinical data for a failed phase III trial of selumetinib combined with docetaxel in lung cancer suggests potential indications in pancreatic and colorectal cancers with KRAS mutation. This data-informed study exemplifies a method for stratified medicine to identify novel cancer subpopulations, their genetic biomarkers, and effective drug combinations. Two drugs, even with the same target, rarely have the same potency across all cancer patients - so how do we objectively select the right patients to treat with each drug? An international effort led by Michael P. Menden and Dennis Wang developed a machine learning approach called SEABED to identify groups of individuals from a population who respond distinctly to specific targeted therapies. They used SEABED to systematically compare 327 pairs of anti-cancer drugs across a panel of >800 cancer cells and 30 cancer types. SEABED identified groups of cells where one drug was more effective than the other. Interestingly, groups responding differently to the pairs of drugs could be treated more effectively when both drugs are given together as a combination, which can be in the presence or absence of drug synergy. This approach enables systematic explorations of personalised medicine to reveal biomarkers and drug combination opportunities.